A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices

A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices. Trabelsi, I., Mahmoudi, B., Minani, J. B., , Moha, N., & Gu�h�neuc, Y. Transactions on Software Engineering (TSE), 51(11):2927–2995, IEEE CS Press, November, 2025. 24 pages.

Paper abstract bibtex

Scalability and maintainability challenges in monolithic systems have led to the adoption of microservices, which divide systems into smaller, independent services. However, migrating existing monolithic systems to microservices is a complex and resource-intensive task, which can benefit from machine learning (ML) to automate some of its phases. Choosing the right ML approach for migration remains challenging for practitioners. Previous works studied separately the objectives, artifacts, techniques, tools, and benefits and challenges of migrating monolithic systems to microservices. No work has yet investigated systematically existing ML approaches for this migration to understand the automated migration phases, inputs used, ML techniques applied, evaluation processes followed, and challenges encountered. We present a systematic literature review (SLR) that aggregates, synthesises, and discusses the approaches and results of 81 primary studies (PSs) published between 2015 and 2024. We followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement to report our findings and answer our research questions (RQs). We extract and analyse data from these PSs to answer our RQs. We synthesise the findings in the form of a classification that shows the usage of ML techniques in migrating monolithic systems to microservices. The findings reveal that some phases of the migration process, such as monitoring and service identification, are well-studied, while others, like packaging microservices, remain unexplored. Additionally, the findings highlight key challenges, including limited data availability, scalability and complexity constraints, insufficient tool support, and the absence of standardized benchmarking, emphasizing the need for more holistic solutions.

@ARTICLE{Trabelsi25-TSE-ML4MS,
   AUTHOR       = {Imen Trabelsi and Brahim Mahmoudi and 
      Jean Baptiste Minani and and Naouel Moha and Yann-Ga�l Gu�h�neuc},
   JOURNAL      = {Transactions on Software Engineering (TSE)},
   TITLE        = {A Systematic Literature Review of Machine Learning 
      Approaches for Migrating Monolithic Systems to Microservices},
   YEAR         = {2025},
   MONTH        = {November},
   NOTE         = {24 pages.},
   NUMBER       = {11},
   PAGES        = {2927&ndash;2995},
   VOLUME       = {51},
   EDITOR       = {Mauro Pezze},
   KEYWORDS     = {Topic: <b>Evolution patterns</b>, 
      Rubrique : <b>patrons d'�volution</b>, Journal: <b>TSE</b>},
   PUBLISHER    = {IEEE CS Press},
   URL          = {http://www.ptidej.net/publications/documents/TSE25b.doc.pdf},
   ABSTRACT     = {Scalability and maintainability challenges in monolithic 
      systems have led to the adoption of microservices, which divide 
      systems into smaller, independent services. However, migrating 
      existing monolithic systems to microservices is a complex and 
      resource-intensive task, which can benefit from machine learning (ML) 
      to automate some of its phases. Choosing the right ML approach for 
      migration remains challenging for practitioners. Previous works 
      studied separately the objectives, artifacts, techniques, tools, and 
      benefits and challenges of migrating monolithic systems to 
      microservices. No work has yet investigated systematically existing 
      ML approaches for this migration to understand the automated 
      migration phases, inputs used, ML techniques applied, evaluation 
      processes followed, and challenges encountered. We present a 
      systematic literature review (SLR) that aggregates, synthesises, and 
      discusses the approaches and results of 81 primary studies (PSs) 
      published between 2015 and 2024. We followed the Preferred Reporting 
      Items for Systematic Review and Meta-Analysis (PRISMA) statement to 
      report our findings and answer our research questions (RQs). We 
      extract and analyse data from these PSs to answer our RQs. We 
      synthesise the findings in the form of a classification that shows 
      the usage of ML techniques in migrating monolithic systems to 
      microservices. The findings reveal that some phases of the migration 
      process, such as monitoring and service identification, are 
      well-studied, while others, like packaging microservices, remain 
      unexplored. Additionally, the findings highlight key challenges, 
      including limited data availability, scalability and complexity 
      constraints, insufficient tool support, and the absence of 
      standardized benchmarking, emphasizing the need for more holistic 
      solutions.}
}

Downloads: 0

{"_id":"YKbj8ag7KSvpp6MLP","bibbaseid":"trabelsi-mahmoudi-minani--moha-guhneuc-asystematicliteraturereviewofmachinelearningapproachesformigratingmonolithicsystemstomicroservices-2025","author_short":["Trabelsi, I.","Mahmoudi, B.","Minani, J. B.","","Moha, N.","Gu�h�neuc, Y."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Imen"],"propositions":[],"lastnames":["Trabelsi"],"suffixes":[]},{"firstnames":["Brahim"],"propositions":[],"lastnames":["Mahmoudi"],"suffixes":[]},{"firstnames":["Jean","Baptiste"],"propositions":[],"lastnames":["Minani"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":[""],"suffixes":[]},{"firstnames":["Naouel"],"propositions":[],"lastnames":["Moha"],"suffixes":[]},{"firstnames":["Yann-Ga�l"],"propositions":[],"lastnames":["Gu�h�neuc"],"suffixes":[]}],"journal":"Transactions on Software Engineering (TSE)","title":"A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices","year":"2025","month":"November","note":"24 pages.","number":"11","pages":"2927–2995","volume":"51","editor":[{"firstnames":["Mauro"],"propositions":[],"lastnames":["Pezze"],"suffixes":[]}],"keywords":"Topic: Evolution patterns, Rubrique : patrons d'�volution, Journal: TSE","publisher":"IEEE CS Press","url":"http://www.ptidej.net/publications/documents/TSE25b.doc.pdf","abstract":"Scalability and maintainability challenges in monolithic systems have led to the adoption of microservices, which divide systems into smaller, independent services. However, migrating existing monolithic systems to microservices is a complex and resource-intensive task, which can benefit from machine learning (ML) to automate some of its phases. Choosing the right ML approach for migration remains challenging for practitioners. Previous works studied separately the objectives, artifacts, techniques, tools, and benefits and challenges of migrating monolithic systems to microservices. No work has yet investigated systematically existing ML approaches for this migration to understand the automated migration phases, inputs used, ML techniques applied, evaluation processes followed, and challenges encountered. We present a systematic literature review (SLR) that aggregates, synthesises, and discusses the approaches and results of 81 primary studies (PSs) published between 2015 and 2024. We followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement to report our findings and answer our research questions (RQs). We extract and analyse data from these PSs to answer our RQs. We synthesise the findings in the form of a classification that shows the usage of ML techniques in migrating monolithic systems to microservices. The findings reveal that some phases of the migration process, such as monitoring and service identification, are well-studied, while others, like packaging microservices, remain unexplored. Additionally, the findings highlight key challenges, including limited data availability, scalability and complexity constraints, insufficient tool support, and the absence of standardized benchmarking, emphasizing the need for more holistic solutions.","bibtex":"@ARTICLE{Trabelsi25-TSE-ML4MS,\r\n AUTHOR = {Imen Trabelsi and Brahim Mahmoudi and \r\n Jean Baptiste Minani and and Naouel Moha and Yann-Ga�l Gu�h�neuc},\r\n JOURNAL = {Transactions on Software Engineering (TSE)},\r\n TITLE = {A Systematic Literature Review of Machine Learning \r\n Approaches for Migrating Monolithic Systems to Microservices},\r\n YEAR = {2025},\r\n MONTH = {November},\r\n NOTE = {24 pages.},\r\n NUMBER = {11},\r\n PAGES = {2927–2995},\r\n VOLUME = {51},\r\n EDITOR = {Mauro Pezze},\r\n KEYWORDS = {Topic: Evolution patterns, \r\n Rubrique : patrons d'�volution, Journal: TSE},\r\n PUBLISHER = {IEEE CS Press},\r\n URL = {http://www.ptidej.net/publications/documents/TSE25b.doc.pdf},\r\n ABSTRACT = {Scalability and maintainability challenges in monolithic \r\n systems have led to the adoption of microservices, which divide \r\n systems into smaller, independent services. However, migrating \r\n existing monolithic systems to microservices is a complex and \r\n resource-intensive task, which can benefit from machine learning (ML) \r\n to automate some of its phases. Choosing the right ML approach for \r\n migration remains challenging for practitioners. Previous works \r\n studied separately the objectives, artifacts, techniques, tools, and \r\n benefits and challenges of migrating monolithic systems to \r\n microservices. No work has yet investigated systematically existing \r\n ML approaches for this migration to understand the automated \r\n migration phases, inputs used, ML techniques applied, evaluation \r\n processes followed, and challenges encountered. We present a \r\n systematic literature review (SLR) that aggregates, synthesises, and \r\n discusses the approaches and results of 81 primary studies (PSs) \r\n published between 2015 and 2024. We followed the Preferred Reporting \r\n Items for Systematic Review and Meta-Analysis (PRISMA) statement to \r\n report our findings and answer our research questions (RQs). We \r\n extract and analyse data from these PSs to answer our RQs. We \r\n synthesise the findings in the form of a classification that shows \r\n the usage of ML techniques in migrating monolithic systems to \r\n microservices. The findings reveal that some phases of the migration \r\n process, such as monitoring and service identification, are \r\n well-studied, while others, like packaging microservices, remain \r\n unexplored. Additionally, the findings highlight key challenges, \r\n including limited data availability, scalability and complexity \r\n constraints, insufficient tool support, and the absence of \r\n standardized benchmarking, emphasizing the need for more holistic \r\n solutions.}\r\n}\r\n\r\n","author_short":["Trabelsi, I.","Mahmoudi, B.","Minani, J. B.","","Moha, N.","Gu�h�neuc, Y."],"editor_short":["Pezze, M."],"key":"Trabelsi25-TSE-ML4MS","id":"Trabelsi25-TSE-ML4MS","bibbaseid":"trabelsi-mahmoudi-minani--moha-guhneuc-asystematicliteraturereviewofmachinelearningapproachesformigratingmonolithicsystemstomicroservices-2025","role":"author","urls":{"Paper":"http://www.ptidej.net/publications/documents/TSE25b.doc.pdf"},"keyword":["Topic: Evolution patterns","Rubrique : patrons d'�volution","Journal: TSE"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://www.yann-gael.gueheneuc.net/Work/Publications/Biblio/complete-bibliography.bib","dataSources":["8vn5MSGYWB4fAx9Z4"],"keywords":["topic: evolution patterns","rubrique : patrons d'�volution","journal: tse"],"search_terms":["systematic","literature","review","machine","learning","approaches","migrating","monolithic","systems","microservices","trabelsi","mahmoudi","minani","","moha","gu�h�neuc"],"title":"A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices","year":2025}